Polarimetric SAR Image Segmentation with B-Splines and a New Statistical Model

TL;DR

This paper introduces a novel polarimetric SAR image segmentation method using B-Spline active contours and a new GHP statistical model to accurately detect region boundaries.

Contribution

It proposes a new statistical model for polarimetric SAR data and integrates it with B-Spline active contours for improved boundary detection.

Findings

Effective boundary detection demonstrated on SAR images

Accurate parameter estimation of the GHP model

Improved segmentation results over existing methods

Abstract

We present an approach for polarimetric Synthetic Aperture Radar (SAR) image region boundary detection based on the use of B-Spline active contours and a new model for polarimetric SAR data: the GHP distribution. In order to detect the boundary of a region, initial B-Spline curves are specified, either automatically or manually, and the proposed algorithm uses a deformable contours technique to find the boundary. In doing this, the parameters of the polarimetric GHP model for the data are estimated, in order to find the transition points between the region being segmented and the surrounding area. This is a local algorithm since it works only on the region to be segmented. Results of its performance are presented.